metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_emotion_ft_0416
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.94
- name: F1
type: f1
value: 0.9399689929524555
- name: Precision
type: precision
value: 0.9171180948520368
distilbert-base-uncased_emotion_ft_0416
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1559
- Accuracy: 0.94
- F1: 0.9400
- Precision: 0.9171
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| 0.7983 | 1.0 | 250 | 0.2761 | 0.91 | 0.9103 | 0.8773 |
| 0.2021 | 2.0 | 500 | 0.1690 | 0.935 | 0.9358 | 0.9022 |
| 0.1342 | 3.0 | 750 | 0.1606 | 0.9385 | 0.9386 | 0.9256 |
| 0.1034 | 4.0 | 1000 | 0.1471 | 0.937 | 0.9367 | 0.9236 |
| 0.0828 | 5.0 | 1250 | 0.1572 | 0.9355 | 0.9355 | 0.9132 |
| 0.0716 | 6.0 | 1500 | 0.1547 | 0.942 | 0.9415 | 0.9305 |
| 0.0595 | 7.0 | 1750 | 0.1584 | 0.9385 | 0.9385 | 0.9170 |
| 0.0514 | 8.0 | 2000 | 0.1559 | 0.94 | 0.9400 | 0.9171 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2